List your company
ResearchFormerly WizWand

Mean Reward on ALFWorld

0.767Mean RewardNO-COMP
-0.030680.176410.38350.59059May 26, 2026
Updated 5mo ago

Evaluation results

MethodLinks
NO-COMPBackbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.767—
AGORABackbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.767100
TruncBackbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.767100
NO-COMPBackbone=gpt-5-mini, Inference Protocol=Inference-free2026.050.767—
AGORABackbone=gpt-5-mini, Inference Protocol=Inference-free2026.050.63383
TruncBackbone=gpt-5-mini, Inference Protocol=Inference-free2026.050.63383
Floor-K2Backbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.678
Floor-K2Backbone=gpt-5-mini, Inference Protocol=Inference-free2026.050.565
LongLinguaBackbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.467100
LongLinguaBackbone=gpt-5-mini, Inference Protocol=Inference-free2026.050.46793
HiAgentBackbone=qwen3.5-flash, Inference Protocol=LLM-call per step2026.050.486
ACONBackbone=qwen3.5-flash, Inference Protocol=LLM-call per step2026.050.486
HiAgentBackbone=gpt-5-mini, Inference Protocol=LLM-call per step2026.050.480
AgentDietBackbone=qwen3.5-flash, Inference Protocol=LLM-call per step2026.050.33371
AGORABackbone=gpt-4o-mini, Inference Protocol=Inference-free2026.050.333111
ObsMaskBackbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.364
NO-COMPBackbone=gpt-4o-mini, Inference Protocol=Inference-free2026.050.3—
TruncBackbone=gpt-4o-mini, Inference Protocol=Inference-free2026.050.26789
ObsMaskBackbone=gpt-5-mini, Inference Protocol=Inference-free2026.050.26753
AgentDietBackbone=gpt-5-mini, Inference Protocol=LLM-call per step2026.050.26753
Floor-K2Backbone=gpt-4o-mini, Inference Protocol=Inference-free2026.050.23378
ACONBackbone=gpt-5-mini, Inference Protocol=LLM-call per step2026.050.23347
AgentDietBackbone=gpt-4o-mini, Inference Protocol=LLM-call per step2026.050.16771
ACONBackbone=gpt-4o-mini, Inference Protocol=LLM-call per step2026.050.16771
ObsMaskBackbone=gpt-4o-mini, Inference Protocol=Inference-free2026.050.143
LongLinguaBackbone=gpt-4o-mini, Inference Protocol=Inference-free2026.050.143
HiAgentBackbone=gpt-4o-mini, Inference Protocol=LLM-call per step2026.050.143
SelCtxBackbone=qwen3.5-flash, Inference Protocol=Inference-free2026.050.0337
SelCtxBackbone=gpt-4o-mini, Inference Protocol=Inference-free2026.0500
SelCtxBackbone=gpt-5-mini, Inference Protocol=Inference-free2026.0500